Rolling simulation device, rolling simulation program, and rolling control system

Abstract

The rolling simulation device executes the following processes: acquiring a control signal used in the control of a plurality of rolling mills from a controller for controlling the plurality of rolling mills via a communication interface; a control signal is inputted to a rolling conveyance model that simulates the conveyance of a material to be rolled in a rolling line to simulate the conveyance of the material to be rolled. Generating analog sensor signals simulating sensor signals output from a plurality of sensors provided in the rolling line on the basis of the simulation result of the rolling conveyance model; acquiring actual sensor signals output from the plurality of sensors; a learning process in which a model correction value for reducing the difference between the analog sensor signal and the actual sensor signal is reflected in the rolling conveyance model; and an abnormality determination process for determining that an abnormal change has occurred in one of the plurality of rolling mills when the difference is equal to or greater than a first threshold value.

Description

Technical Field

[0001] The present disclosure relates to techniques for simulating a rolling line. Background Art

[0002] Patent document 1 discloses a rolling simulation device that simulates the state of a rolling production line. Specifically, the rolling simulation device uses a model formula that simulates each process in the rolling production line to calculate the target value of the rolling of the metal material and the predicted value of the state of the rolled material when the process is changed. Furthermore, the rolling simulation device updates the parameters of the model formula based on the comparison value obtained by comparing the predicted value of the state of the rolled material with the control target value of the actuator used to drive the rolling production line. As a result, parameters that change over the years are updated, which can improve the prediction accuracy of the model formula.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: International Publication No. 2016 / 038705 Summary of the invention

[0006] Problems to be solved by the invention

[0007] The rolling state of a rolling line is represented by the measured value of a sensor installed in the rolling line. As one of the reasons why the measured value of the rolling state becomes inappropriate, it is considered that an abnormal change has occurred in any of the rolling mills constituting the rolling line. In this case, the model simulating the rolling line is not changed, and the operator is notified of the abnormal change in the rolling mill. However, in the rolling simulation device shown in Patent Document 1, the change is determined to be caused by the degradation of the rolling mill over the years, and the model formula is updated. As a result, despite the abnormality, the operation of the rolling line may continue without interruption.

[0008] Furthermore, an inappropriate setting value of a control signal input to a rolling mill may also cause an inappropriate measured value of the rolling state. In this case, the rolling simulation device shown in Patent Document 1 does not detect abnormalities in the rolling state of the rolling line and updates the model formula.

[0009] An object of the present disclosure is to provide a technology capable of improving the accuracy of a model simulating a rolling line and detecting an abnormality in a rolling state of the rolling line.

[0010] Means used to solve problems

[0011] The first viewpoint of the present disclosure relates to a rolling simulation device that simulates a rolling production line in which a plurality of rolling mills are arranged in sequence from the upstream side. The rolling simulation device comprises: a processor connected to a controller that controls the plurality of rolling mills via a communication interface; and a storage device that stores a rolling conveying model that simulates the conveying of rolled materials in the rolling production line. The processor performs the following processing: obtaining a control signal used in the control of the plurality of rolling mills from the controller; inputting the control signal into the rolling conveying model to simulate the conveying of the rolled materials; generating a simulated sensor signal that simulates the sensor signal output from a plurality of sensors provided in the rolling production line based on the simulation result of the rolling conveying model; obtaining the actual sensor signal output from the plurality of sensors; a learning process that causes a model correction value for reducing the difference between the simulated sensor signal and the actual sensor signal to be reflected in the rolling conveying model; and an abnormality determination process that determines that an abnormal change has occurred in one of the plurality of rolling mills when the difference is greater than a first threshold.

[0012] The second viewpoint of the present disclosure relates to a rolling control system for controlling a rolling line in which a plurality of rolling mills are arranged in sequence from the upstream side. The rolling control system comprises: a controller for controlling the plurality of rolling mills via a communication interface; a host device connected to the upstream of the controller and generating set values ​​of control signals input to the plurality of rolling mills via the controller; and a rolling simulation device arranged in parallel between the plurality of rolling mills and the controller and simulating the transportation of the rolled material using a rolling conveying model simulating the transportation of the rolled material in the rolling line. When the plurality of rolling mills and the controller are in a non-connected state and the plurality of sensors arranged in the rolling line and the controller are in a non-connected state, the rolling simulation device performs the following processing: obtaining a control signal used in controlling the plurality of rolling mills from the controller; inputting the control signal into the rolling conveying model to simulate the transportation of the rolled material; generating a simulated sensor signal simulating the sensor signal output from the plurality of sensors based on the simulation result of the rolling conveying model; and outputting the simulated sensor signal to the controller. In addition, the host device performs a determination process for determining whether the rolling state of the rolling line is within an appropriate range based on the simulated sensor signal.

[0013] The actions of the processor may be achieved by executing a rolling simulation program by the processor.

[0014] Effects of the Invention

[0015] According to the first viewpoint of the present disclosure, a control signal for controlling a plurality of rolling mills arranged in sequence from the upstream side in a rolling production line is obtained from a controller for controlling a plurality of rolling mills. The control signal is input into a rolling conveying model that simulates the conveying of a rolled material in a rolling production line, and the conveying of the rolled material is simulated. Then, based on the simulation result of the rolling conveying model, a simulated sensor signal simulating the sensor signal output from a plurality of sensors arranged in the rolling production line is generated. In addition, the actual sensor signal output from the plurality of sensors is obtained in parallel with the generation of the simulated sensor signal. Then, the rolling conveying model is learned by reflecting a model correction value for reducing the difference between the simulated sensor signal and the actual sensor signal in the rolling conveying model. However, when the difference is greater than a first threshold value, it is determined that an abnormal change has occurred in any of the plurality of rolling mills. Thus, by learning based on the difference between the simulated sensor signal and the actual sensor signal, the accuracy of the rolling conveying model can be further improved, and the abnormality of the rolling state of the rolling production line can be detected.

[0016] According to the second viewpoint of the present disclosure, when a plurality of rolling mills are in a non-connected state with the controller and a plurality of sensors provided in the rolling line are in a non-connected state with the controller, a control signal for controlling the plurality of rolling mills is obtained from the controller. The control signal is input into a rolling conveying model simulating the conveying of the rolled material in the rolling line, and the conveying of the rolled material is simulated. Then, based on the simulation result of the rolling conveying model, a simulated sensor signal simulating the sensor signal output from the plurality of sensors is generated. Thereafter, based on the simulated sensor signal, it is determined whether the rolling state of the rolling line is within an appropriate range. Thus, when the rolling state of the rolling line 2 is inappropriate, it is possible to detect the abnormality of the rolling state of the rolling line and confirm whether the setting value of the control signal is appropriate. Furthermore, when a part of the rolling line is changed or a new rolling line is provided, the operation of the rolling line is started on the basis of confirming that the setting value of the control signal is appropriate. Therefore, during the operation of the rolling line, the frequency of adjusting the setting value of the control signal input to the plurality of rolling mills is reduced, and it is possible to expect an improvement in the finishing accuracy of the rolled material. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a diagram for explaining the outline of the rolling control system according to the first embodiment.

[0018] Figure 2 This is a block diagram showing a configuration example of the rolling simulation device according to the first embodiment.

[0019] Figure 3 This is a block diagram showing a processing example of the rolling simulation device according to the first embodiment.

[0020] Figure 4 This is a flowchart showing a processing example of the rolling simulation device according to the first embodiment.

[0021] Figure 5 This is a diagram for explaining the outline of the rolling control system according to the second embodiment.

[0022] Figure 6 This is a block diagram showing a processing example of the rolling control system according to the second embodiment.

[0023] Figure 7 This is a flowchart showing a processing example of the rolling control system according to the second embodiment.

[0024] Description of Reference Numerals

[0025] 1A, 1B…rolling control system, 2…rolling production line, 3…rolled material, 4…rolling mill, 6…sensor, 7…actuator, 8…controller, 10…rolling simulation device, 11…simulation processing, 12…differential judgment processing, 13…model correction value generation processing, 14…saving processing, 20…processor, 30…storage device, 31…rolling conveying model, 32…rolling simulation program, 50…host device, 51…generation processing of control signal setting value, 52…rolling state judgment processing, 53…change processing of control signal setting value. DETAILED DESCRIPTION

[0026] A rolling control system, a rolling simulation device, and a rolling simulation program according to an embodiment of the present disclosure will be described with reference to the accompanying drawings. In addition, the same reference numerals are given to common elements in the drawings, and duplicate descriptions are omitted.

[0027] 1. Implementation Method 1

[0028] 1-1. Overview of rolling control system

[0029] Figure 1 This is a diagram for explaining the outline of a rolling control system 1A according to Embodiment 1. The rolling control system 1A controls a rolling line 2. The rolling line 2 is, for example, a hot rolling line or a cold rolling line. The rolling line 2 includes a plurality of rolling mills 4 arranged in parallel along a conveying direction of a rolled material 3. That is, the rolling line 2 is provided with a plurality of rolling mills 4 arranged in sequence from the upstream side.

[0030] The rolling production line 2 also includes a plurality of sensors 6. The plurality of sensors 6 measure the rolling state of the rolled material 3. The plurality of sensors 6 can be, for example, arranged on the input side of the rolling mill 4 that is the first (most upstream side) in the conveying direction of the rolled material 3, or can be arranged on the output side of the rolling mill 4 that is the last (most downstream side) in the conveying direction of the rolled material 3, or can be arranged between the rolling mills 4. That is, there are various places where the plurality of sensors 6 are arranged. As the plurality of sensors 6, a plate speed meter, a plate thickness meter, etc. are exemplified. In addition, the information obtained by the plurality of sensors 6 is input to the controller 8. In addition, the information obtained by the sensor 6 is also referred to as an actual sensor signal.

[0031] The plurality of rolling mills 4 each include an actuator 7 and are driven by the actuator 7. The actuator 7 is provided for each rolling mill 4. The actuator 7 is driven and controlled according to a control signal output from a controller 8. The control signal output from the controller 8 is, for example, a parameter input to the actuator 7. As parameters, the rotation speed of the roll included in the rolling mill 4, the opening of the roll, etc. are exemplified. The parameters input to the actuator 7 may be generated by the controller 8 or by the host device 50.

[0032] The rolling recording system 1 includes the above-mentioned rolling line 2 , a controller 8 , a rolling simulation device 10 , and a host device 50 .

[0033] The controller 8 controls the plurality of rolling mills 4 via the communication interface. Specifically, the controller 8 performs sequential control of the control signals input to the actuator 7 and control of sending the prescribed information to the host device 50. The prescribed information includes the actual sensor signal (measured value of the rolling state, etc.) obtained by the sensor 6. In addition, the prescribed information may also include related information of the control signal (information of the control signal input to the actuator 7, etc.).

[0034] The controller 8 may include, for example, one or more processors (not shown) and one or more storage devices (not shown), or one or more dedicated hardware (not shown). As a specific example, the controller 8 is a PLC (Programmable Logic Controller).

[0035] The host device 50 manages the rolling state of the rolling line 2. Specifically, the host device 50 generates a set value (parameter) of a control signal input to the rolling mill 4 (actuator 7). The set value of the control signal can be generated based on a simulation result analyzed by a dedicated tool for simulating the rolling state of the rolling line 2, or can be generated based on a difference value between a predicted value of the rolling state based on the simulation result and an actual sensor signal. In addition, the set value of the control signal is also referred to as a control signal.

[0036] The host device 50 is connected upstream of the controller 8. The host device 50 includes, for example, one or more processors (not shown) and one or more storage devices (not shown).

[0037] The rolling simulation device 10 simulates the transportation of the rolled material 3 in the rolling production line 2. In the simulation of the transportation of the rolled material 3, a rolling transportation model (not shown) that simulates the transportation of the rolled material 3 is used. The rolling transportation model here is based on a model that has undergone a certain level of learning. Based on this, for example, when the rolling state obtained from the rolling transportation model is different from the actual rolling state, the rolling simulation device 10 determines whether it is necessary to further improve the accuracy of the rolling transportation model, whether the rolling mill 4 has an abnormality, etc. In this way, the accuracy of the rolling transportation model can be further improved, and the abnormality of the rolling state of the rolling production line 2 can be detected.

[0038] The outline of the processing of the rolling simulation device 10 is as follows. The rolling simulation device 10 performs the following processing: obtaining a control signal used in the control of the plurality of rolling mills 4 from the controller 8 that controls the plurality of rolling mills 4 arranged in sequence from the upstream side in the rolling production line 2; inputting the control signal into the rolling conveying model to simulate the conveying of the rolled material 3; generating a simulated sensor signal simulating the sensor signal output from the plurality of sensors 6 provided in the rolling production line 2 based on the simulation result of the rolling conveying model; obtaining the actual sensor signal output from the plurality of sensors 6; learning processing, so that the model correction value for reducing the difference between the simulated sensor signal and the actual sensor signal is reflected in the rolling conveying model; and abnormality determination processing, when the difference is greater than the first threshold value, determining that an abnormal change has occurred in one of the plurality of rolling mills. The details of the processing of the rolling simulation device 10 will be described later.

[0039] Consider the location where the rolling simulation device 10 is set. In the rolling simulation device 10, a process of comparing the difference between the simulated sensor signal and the actual sensor signal is performed. In this case, it is preferred that the difference between the time when the simulated sensor signal is generated by the rolling simulation device 10 and the time when the actual sensor signal is obtained by the rolling simulation device 10 is smaller. On the other hand, it is assumed that the time from when the set value of the control signal is input to the rolling mill 4 to when the sensor 6 outputs the actual sensor signal is shorter. Therefore, the rolling simulation device 10 is preferably set on the downstream side of the controller 8 in the same manner as the rolling mill 4. Therefore, the rolling simulation device 10 is set in parallel between a plurality of rolling mills 4 and the controller 8.

[0040] 1-2. Example of rolling simulation device

[0041] 1-2-1. Configuration example

[0042] Figure 2 This is a block diagram showing a configuration example of the rolling simulation device 10 according to the first embodiment.

[0043] The rolling simulation device 10 includes one or more processors 20 (hereinafter referred to as the processor 20) and one or more storage devices 30 (hereinafter referred to as the storage device 30). The processor 20 performs various processes. As the processor 20, a CPU (Central Processing Unit) is exemplified. The storage device 30 stores various information required for the processing of the processor 20. As the storage device 30, a volatile memory, a non-volatile memory, a HDD (Hard Disk Drive), an SSD (Solid State Drive), etc. can be exemplified.

[0044] The various information stored in the storage device 30 includes a rolling conveying model 31 and a rolling simulation program. As described above, the rolling conveying model 31 is a model for simulating the conveying of the rolled material 3 of the rolling production line 2. The rolling simulation program (not shown) is a computer program executed by the processor 20. The rolling simulation program can also be executed by the processor 20 to realize various functions of the rolling simulation device 10. In addition, the rolling simulation program is not limited to the storage device 30, and can also be recorded in a computer-readable storage medium.

[0045] 1-2-2. Processing example

[0046] Figure 3 It is a block diagram showing a processing example of the rolling simulation device 10 according to the embodiment.

[0047] Specifically, the rolling simulation device 10 (more specifically, the processor 20) inputs the control signal output from the controller 8. Then, the rolling simulation device 10 performs a simulation process 11 for simulating the conveyance of the rolled material 3 based on the control signal. In the simulation process 11, a process of reading the rolling conveyance model 31 stored in the storage device 30 is performed. In addition, in the simulation process 11, the rolling simulation device 10 generates a simulated sensor signal that simulates the sensor signal output from the plurality of sensors 6 based on the simulation result of the rolling conveyance model 31.

[0048] Furthermore, the rolling simulation device 10 obtains actual sensor signals output from a plurality of sensors 6. Then, the rolling simulation device 10 performs a differential determination process 12 based on the simulated sensor signal and the actual sensor signal. In the differential determination process 12, the rolling simulation device 10 determines whether the difference between the simulated sensor signal and the actual sensor signal is less than a first threshold value. When the difference is less than the first threshold value, the rolling simulation device 10 performs a model correction value generation process 13 for generating a model correction value for reducing the difference. After executing the model correction value generation process 13, the rolling simulation device 10 performs a learning process for reflecting the model correction value in the rolling conveying model 31. Thus, the accuracy of the rolling conveying model 31 can be further improved.

[0049] In addition, when the difference is small, it is considered that the rolling conveying model has a certain degree of accuracy. In this case, the rolling simulation device 10 may not reflect the difference in the rolling conveying model. Therefore, the rolling simulation device 10 may also reflect the model correction value in the rolling conveying model 31 in the learning process when the difference is less than the first threshold and is greater than the second threshold that is smaller than the first threshold.

[0050] On the other hand, when the difference is greater than the first threshold value, the rolling simulation device 10 performs an abnormal determination process in the differential determination process 12 to determine that an abnormal change has occurred in any one of the plurality of rolling mills 4. In this case, the rolling simulation device 10 notifies the host device 50 of the abnormal change of the rolling mill 4 via the controller 8. Thus, it is possible to detect an abnormality in the rolling state of the rolling production line 2. In addition, the abnormal change of the rolling mill 4 refers to, for example, a change in a parameter indicating the state of the rolling mill 4 that is greater than a prescribed value. As the main reason why the change in the parameter is greater than the prescribed value, examples include age-related degradation of the rolling mill 4 and a failure of the rolling mill 4.

[0051] In addition, the rolling simulation device 10 may also perform a storage process 14 of storing the difference value between the simulated sensor signal and the actual sensor signal and the state of various sensor signals after executing the difference determination process 12. Thus, it is possible to confirm the history of the difference value and the state of various sensor signals when the cause of the inappropriate rolling state of the rolling line 2 occurs. Therefore, it is easy to determine the cause of the inappropriate rolling state of the rolling line.

[0052] Figure 4 This is a flowchart schematically showing a processing example of the rolling simulation device 10 .

[0053] In step S100 , the rolling simulation device 10 acquires various information. Thereafter, the process proceeds to step S110 . The various information includes a control signal output from the controller 8 and actual sensor signals output from the plurality of sensors 6 .

[0054] In step S110, the rolling simulation device 10 simulates the conveyance of the rolled material 3 using the rolling conveyance model 31. Thereafter, the process proceeds to step S120.

[0055] In step S120, the rolling simulation device 10 generates a simulated sensor signal simulating the sensor signals output from the plurality of sensors 6 based on the simulation result of the rolling conveyance model 31. Thereafter, the process proceeds to step S130.

[0056] In step S130, the rolling simulation device 10 calculates the difference between the simulated sensor signal and the actual sensor signal. Thereafter, the process proceeds to step S140.

[0057] In step S140, the rolling simulation device 10 determines whether the difference between the simulated sensor signal and the actual sensor signal is less than a threshold value. If it is determined that the difference is less than the threshold value (step S140; yes), the process proceeds to step S150. Otherwise (step S140; no), the process proceeds to step S170.

[0058] In step S150, the rolling simulation device 10 generates a model correction value for reducing the difference. Thereafter, the process proceeds to step S160.

[0059] In step S160 , the rolling simulation device 10 performs a learning process for reflecting the model correction value on the rolling conveyance model 31 .

[0060] Furthermore, as described above, when the difference is smaller than the first threshold value and is equal to or larger than the second threshold value which is smaller than the first threshold value, the rolling simulation device 10 may reflect the model correction value on the rolling conveyance model 31 .

[0061] In step S170, the rolling simulation device 10 determines that an abnormal change has occurred in any one of the plurality of rolling mills 4. Thereafter, the process proceeds to step S180.

[0062] In step S180 , the rolling simulation device 10 notifies the host device 50 via the controller 8 that the rolling mill 4 has undergone an abnormal change.

[0063] 1-3. Effect

[0064] According to the present embodiment, a control signal for controlling the plurality of rolling mills 4 is obtained from a controller 8 that controls the plurality of rolling mills 4 arranged in sequence from the upstream side in the rolling line 2. The control signal is input to a rolling conveying model 31 that simulates the conveying of the rolled material 3 in the rolling line 2, and the conveying of the rolled material 3 is simulated. Then, based on the simulation result of the rolling conveying model 31, a simulated sensor signal simulating the sensor signal output from the plurality of sensors 6 provided in the rolling line 2 is generated. In addition, in parallel with the generation of the simulated sensor signal, the actual sensor signal output from the plurality of sensors 6 is obtained. Then, by reflecting the model correction value for reducing the difference between the simulated sensor signal and the actual sensor signal on the rolling conveying model 31, the rolling conveying model 31 is learned. However, when the difference is greater than the first threshold value, it is determined that an abnormal change has occurred in any of the plurality of rolling mills 4. Thus, by learning based on the difference between the simulated sensor signal and the actual sensor signal, the accuracy of the rolling conveying model 31 can be further improved, and the abnormality of the rolling state of the rolling line 2 can be detected.

[0065] 2. Implementation Method 2

[0066] 2-1. Overview of rolling control system

[0067] Figure 5 This is a diagram for explaining the outline of the rolling control system 1B of the second embodiment. For example, it is considered that the reason why the rolling state of the rolling line 2 is inappropriate is neither the accuracy of the rolling conveying model nor the abnormal change of the rolling mill 4, but the setting value of the control signal input to the rolling mill 4. In this case, in the rolling simulation device 10 of the rolling control system 1A of the above-mentioned first embodiment, the cause cannot be determined. Therefore, in the rolling control system 1B, when the rolling state of the rolling line 2 is inappropriate, it is determined whether the setting values ​​of the control signals input to the plurality of rolling mills 4 are appropriate.

[0068] The basic structure of the rolling control system 1B is the same as that of the rolling control system 1A described above. Figure 5 As shown, there can be cited points where a plurality of rolling mills 4 and the controller 8 become in a non-connected state (first non-connected state), points where a plurality of sensors 6 and the controller 8 become in a non-connected state (second non-connected state), and points where the simulated sensor signal generated by the rolling simulation device 10 is output to the controller 8, etc.

[0069] The first non-connected state is, for example, a state where the wiring between the plurality of rolling mills 4 and the controller 8 is cut off, a state where the control signal input to the rolling mill 4 (actuator 7) is restricted from being used, etc. The second non-connected state is, for example, a state where the wiring between the plurality of sensors 6 and the controller 8 is cut off, a state where the output of the sensor signal from the sensor 6 is restricted, etc.

[0070] In addition, the switching between the rolling control system 1A and the rolling control system 1B is controlled by the host device 50. For example, when the operation mode of the rolling line 2 is the operation mode, the rolling control system 1A is selected, and when the operation mode of the rolling line 2 is the inspection mode, the rolling control system 1B is selected. And, when the rolling control system 1B is selected, the switching to the first non-connected state and the switching to the second non-connected state are performed.

[0071] The outline of the processing of the rolling control system 1B is as follows. When the plurality of rolling mills 4 and the controller 8 are in a non-connected state, and the plurality of sensors 6 and the controller 8 are in a non-connected state, the rolling control system 1B performs the following processing: obtaining control signals used in the control of the plurality of rolling mills 4 from the controller 8 that controls the plurality of rolling mills 4; inputting control signals to the rolling conveying model 31 to simulate the conveying of the rolled material 3; generating simulated sensor signals simulating sensor signals output from the plurality of sensors 6 provided in the rolling production line 2 based on the simulation results of the rolling conveying model 31; outputting the simulated sensor signals to the controller 8; and determining whether the rolling state of the rolling production line 2 is within an appropriate range based on the simulated sensor signals. The details of the processing of the rolling control system 1B will be described later.

[0072] 2-2. Processing example

[0073] Figure 6 This is a block diagram showing a processing example of the rolling control system 1B according to Embodiment 2. The processing of the rolling control system 1B includes processing of each of the rolling simulation device 10 and the host device 50 .

[0074] The processing example of the rolling simulation device 10 is described. Specifically, the rolling simulation device 10 (processor 20) receives a control signal output from the controller 8. Then, the rolling simulation device 10 performs a simulation process 11 for simulating the transportation of the rolled material 3 based on the control signal. In addition, in the simulation process 11, the rolling simulation device 10 generates a simulated sensor signal that simulates the sensor signal output from the plurality of sensors 6 based on the simulation result of the rolling transportation model 31. Thereafter, the rolling simulation device 10 outputs the simulated sensor signal to the controller 8.

[0075] Next, a processing example of the host device 50 will be described. Specifically, the host device 50 executes a process of generating a set value of a control signal (generation process 51 of the set value of the control signal). After executing the generation process 51 of the set value of the control signal, the host device 50 outputs the control signal to the rolling simulation device 10 via the controller 8. In addition, the host device 50 acquires an analog sensor signal output from the rolling simulation device 10 via the controller 8. Then, the host device 50 executes a process of determining whether the rolling state of the rolling production line 2 is within an appropriate range based on the analog sensor signal (determination process 52 of the rolling state). After that, when the host device 50 determines that the rolling state of the rolling production line 2 is not within the appropriate range, the host device 50 executes a process of changing the set value of the control signal (change process 53 of the set value of the control signal). In addition, as Figure 6 shown, the determination process 52 of the rolling state includes an abnormality determination process. The abnormality determination process is a process of determining that an abnormal change has occurred in any one of the plurality of rolling mills 4 when it is determined that the rolling state of the rolling production line 2 is not within the appropriate range. Thereby, an abnormality in the rolling state of the rolling production line 2 can be detected.

[0076] Figure 7 is a flowchart schematically showing a processing example of the rolling control system 1B.

[0077] In step S200, the rolling control system 1B generates a set value of a control signal. After that, the process proceeds to step S210.

[0078] In step S210, the rolling control system 1B inputs a control signal to the rolling conveyance model 31 to simulate the conveyance of the material to be rolled 3. After that, the process proceeds to step S220.

[0079] In step S220, the rolling control system 1B generates an analog sensor signal that simulates the sensor signals output from the plurality of sensors 6 based on the simulation result of the rolling conveyance model 31. After that, the process proceeds to step S230.

[0080] In step S230, the rolling control system 1B determines whether the rolling state of the rolling production line 2 is within an appropriate range. When it is determined that the rolling state of the rolling production line 2 is within the appropriate range (step S230; YES), the process ends. In other cases (step S230; NO), the process proceeds to step S240.

[0081] In step S240, the rolling control system 1B changes the set value of the control signal.

[0082] 2-3. Effects

[0083] According to the present embodiment, when the plurality of rolling mills 4 and the controller 8 are in a non-connected state, and the plurality of sensors 6 provided in the rolling line 2 and the controller 8 are in a non-connected state, a control signal for controlling the plurality of rolling mills 4 is obtained from the controller 8. The control signal is input into a rolling conveying model 31 that simulates the conveying of the rolled material 3 in the rolling line 2, and the conveying of the rolled material 3 is simulated. Then, based on the simulation result of the rolling conveying model 31, a simulated sensor signal simulating the sensor signal output from the plurality of sensors 6 is generated. Thereafter, based on the simulated sensor signal, it is determined whether the rolling state of the rolling line 2 is within an appropriate range. Thus, when the rolling state of the rolling line 2 is inappropriate, it is possible to detect the abnormality of the rolling state of the rolling line 2, and to confirm whether the set value of the control signal is appropriate.

[0084] Furthermore, when a part of the rolling line 2 is changed or a new rolling line 2 is installed, the operation of the rolling line 2 is started after confirming that the set value of the control signal is appropriate. Therefore, during the operation of the rolling line 2, the frequency of adjusting the set value of the control signal input to the plurality of rolling mills 4 is reduced, and it can be expected that the finishing accuracy of the rolled material 3 will be improved.

Claims

1. A rolling simulation device, simulating a rolling production line in which multiple rolling mills are arranged in sequence from the upstream side, It is characterized in that The rolling simulation device has: a processor connected to a controller for controlling the plurality of rolling mills via a communication interface; and a storage device storing a rolling conveying model simulating the conveying of the rolled material in the rolling production line; The processor is configured to perform the following processing: obtaining a control signal for controlling the plurality of rolling mills from the controller; Inputting the control signal into the rolling conveying model to simulate the conveying of the rolled material; generating, based on the simulation result of the rolling conveying model, a simulated sensor signal simulating sensor signals output from a plurality of sensors provided in the rolling line; obtaining actual sensor signals output from the plurality of sensors; A learning process for reflecting a model correction value for reducing a difference between the simulated sensor signal and the actual sensor signal in the rolling conveying model; and The abnormality determination process determines that an abnormal change has occurred in any one of the plurality of rolling mills when the difference is equal to or greater than a first threshold value.

2. The rolling simulation device according to claim 1, It is characterized in that The processor is configured to further execute a process of notifying a higher-level device connected upstream of the controller that an abnormal change has occurred in the rolling mill when the difference is equal to or greater than the first threshold.

3. The rolling simulation device according to claim 1 or 2, It is characterized in that The processor is configured so that, in the learning process, When the difference is smaller than a first threshold value and is equal to or larger than a second threshold value which is smaller than the first threshold value, the model correction value is reflected in the rolling conveyance model.

4. A rolling simulation program that simulates a rolling production line with multiple rolling mills arranged in sequence from the upstream side. It is characterized in that The rolling simulation program is configured to cause the computer to execute the following processing: acquiring a control signal used in controlling the plurality of rolling mills from a controller connected to a controller that controls the plurality of rolling mills via a communication interface; Inputting the control signal into a rolling conveying model simulating the conveying of the rolled material in the rolling production line to simulate the conveying of the rolled material; generating a simulated sensor signal simulating sensor signals output from a plurality of sensors provided in the rolling line based on a simulation result of the rolling conveying model; obtaining actual sensor signals output from the plurality of sensors; A learning process for reflecting a model correction value for reducing a difference between the simulated sensor signal and the actual sensor signal in the rolling conveying model; and The abnormality determination process determines that an abnormal change has occurred in any one of the plurality of rolling mills when the difference is equal to or greater than a first threshold value.

5. A rolling control system that controls a rolling production line in which multiple rolling mills are arranged in sequence from the upstream side. It is characterized in that The rolling control system has: a controller for controlling the plurality of rolling mills via a communication interface; a host device connected upstream of the controller to generate set values ​​of control signals input to the plurality of rolling mills via the controller; as well as A rolling simulation device is arranged in parallel between the plurality of rolling mills and the controller, and uses a rolling conveying model that simulates the conveying of the rolled material in the rolling production line to simulate the conveying of the rolled material. The rolling simulation device is configured to perform the following processing when the plurality of rolling mills and the controller are disconnected and the plurality of sensors provided in the rolling line and the controller are disconnected: obtaining a control signal for controlling the plurality of rolling mills from the controller; Inputting the control signal into the rolling conveying model to simulate the conveying of the rolled material; generating a simulated sensor signal simulating sensor signals output from the plurality of sensors based on a simulation result of the rolling conveying model; as well as outputting the analog sensor signal to the controller, The host device is configured to execute a determination process of determining whether a rolling state of the rolling line is within an appropriate range based on the analog sensor signal.

6. The rolling control system according to claim 5, It is characterized in that The host device is configured to change the set value of the control signal when the rolling state is not within the appropriate range in the determination process.

Images